metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0190)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | MAE |
| Split | train |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 190 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8324 |
| Val Accuracy | 0.7357 |
| Test Accuracy | 0.7372 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, pear, orange, bed, forest, lobster, camel, wolf, poppy, tank, wardrobe, lion, bear, chimpanzee, possum, castle, table, cattle, woman, pine_tree, plain, dolphin, lizard, bicycle, mouse, crocodile, plate, cloud, shark, lamp, clock, orchid, raccoon, rabbit, house, mountain, beaver, otter, cockroach, dinosaur, seal, elephant, flatfish, skyscraper, tiger, sunflower, whale, squirrel, boy, porcupine